Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/huifer/claude-code-interview/export-pdfgit clone --depth 1 https://github.com/huifer/claude-code-interviewWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00033 | $0.02742 |
| Opus 5 | $0.00016 | $0.01371 |
| Sonnet 5 | $0.00007 | $0.00548 |
| Haiku 4.5 | $0.00003 | $0.00274 |
Grade A, and why
export-pdf scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.
导出PDF简历
将简历变体 $1 导出为PDF格式。可选使用模板 $2。
使用方法
基础用法
# 导出默认模板
/resume/export-pdf google_v2
# 使用指定模板
/resume/export-pdf google_v2 modern
# 导出到指定位置
/resume/export-pdf google_v2 professional ~/Downloads/
可用模板
1. classic (推荐 - 最ATS友好)
特点:
- 简洁单列布局
- 标准字体（Times New Roman）
- 最适合ATS系统
- 黑白打印友好
适用:
- 大公司（Workday ATS）
- 保守行业（金融、政府）
- 需要打印的场合
2. modern (推荐 - 平衡美观和可读性)
特点:
- 轻微格式化（加粗标题）
- 使用Calibri字体
- ATS兼容性良好
- 适合大多数公司
适用:
- 科技公司（Greenhouse/Lever ATS）
- 中型公司
- 一般求职场景
3. creative (初创公司友好)
特点:
- 现代化设计
- 支持颜色和图标
- 强调个人品牌
- ATS兼容性中等
适用:
- 初创公司
- 设计/创意岗位
- 强调个人风格
4. technical (技术岗位专用)
特点:
- 突出技术技能
- GitHub/项目链接突出显示
- 包含技术栈可视化
- ATS兼容性良好
适用:
- 软件工程师岗位
- 技术主导的公司
- 需要展示技术深度
PDF导出流程
步骤 1: 读取简历变体
# 读取JSON格式的简历变体
Read: data/resume/variants/google_v2.json
步骤 2: 转换为Markdown
将JSON转换为结构化Markdown：
# Li Ming
**Senior Software Engineer**
📍 Beijing, China | 📧 [email protected]
🔗 linkedin.com/in/liming-dev | 💻 github.com/liming-dev
## Professional Summary
Senior Software Engineer with 5+ years of experience in distributed systems
and cloud computing. Expert in Python and Go, with deep expertise in
microservices architecture and system optimization.
## Technical Skills
### Programming Languages
Python (Expert), Go (Intermediate), Java (Advanced), TypeScript (Advanced)
### Frameworks & Tools
Django, FastAPI, Spring Boot, React, Kubernetes, Docker, AWS, PostgreSQL, Redis
### Core Competencies
- Microservices Architecture
- Distributed Systems
- Cloud Computing (AWS/GCP)
- System Design & Scalability
- CI/CD & DevOps
## Work Experience
### ByteDance | Senior Software Engineer
**March 2022 - Present | Beijing**
Designed and implemented high-concurrency order processing system:
- Scaled peak QPS from 5k to 50k (900% improvement)
- Achieved 99.99% system availability
- Reduced service latency by 60% through optimization
- Led team of 5 engineers in microservices migration
### Meituan | Software Engineer
**July 2019 - February 2022 | Beijing**
Developed food delivery dispatch system:
- Optimized delivery routing algorithms, reducing average time by 12%
- Implemented distributed caching, reducing database load by 70%
- Refactored monolithic application into 10+ microservices
## Projects
### Distributed Task Scheduler
**Creator | June 2021 - Present**
- GitHub: github.com/liming-dev/task-scheduler
- 1.5k+ GitHub stars, used by 3 companies in production
- Supports 100k+ tasks/second per cluster
- Implemented graceful failover and data consistency
### Real-time Analytics Dashboard
**Core Contributor | September 2020 - December 2021**
- GitHub: github.com/liming-dev/analytics-dashboard
- 800+ GitHub stars
- Efficient aggregation algorithms, 50% faster than commercial tools
- Real-time data visualization supporting millions of data points
## Education
### Tsinghua University | Master of Computer Science
**September 2017 - June 2019 | Beijing**
- GPA: 3.8/4.0
- Honors: Outstanding Graduate, National Scholarship
### Zhejiang University | Bachelor of Software Engineering
**September 2013 - June 2017 | Hangzhou**
- GPA: 3.7/4.0
- Honors: Provincial Outstanding Graduate
## Certifications
- **AWS Certified Solutions Architect** (Amazon Web Services, 2021)
- **Google Cloud Professional Cloud Architect** (Google Cloud, 2022)
## Languages
- **Chinese**: Native
- **English**: Advanced
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 407 lines · 33 tokens per session scan A 6015f5c4595a
export-pdf is a command published in the GitHub repository huifer/claude-code-interview (23 stars, last pushed 7mo ago), licensed MIT. It adds 33 tokens to every session and 2,742 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.